R

roxanneardary

Trionyx is a multi-agent robotics fleet intelligence platform that coordinates autonomous robots through a shared world model, dynamic task graphs, and real-time scheduling. It focuses on distributed decision-making, simulation-first validation, and adaptive optimization to manage complex warehouse and industrial operations.

TotalRemote is an open-source universal TV control system that unifies multiple control methods—including IR, HDMI-CEC, and smart TV APIs—into a single, plugin-based platform. It provides a consistent command layer for different devices, supports automatic device discovery, and integrates with smart home systems like Home Assistant and MQTT for automation.

The Modular Non-Invasive BCI Engineering Platform is an open-source, AGPL-3.0+ neuroengineering framework designed to unify wearable brain-computer interfaces, hardware abstraction, and real-time neural decoding into a single modular system. It enables developers to build, simulate, and deploy EEG-based applications through interchangeable wearable and hardware modules, supported by machine learning pipelines, sleep and dream state analysis, hardware development tooling, and legal assurance systems for design validation and compliance.

LAVE (Low-Altitude Vehicle Experiment) is an open-source research platform exploring human-scale hover in the sub-meter regime using distributed electric thrust, real-time stabilization, and fully transparent hardware and software systems. Built for reproducibility and experimentation rather than productization, it focuses on measuring the unstable transition between ground contact and sustained flight, with all telemetry, failures, and design iterations openly shared as part of the research process.

KineticKind is an open-source SUV platform designed to make entering and exiting a vehicle safe, comfortable, and dignified through intelligent seat-assist technology. By combining rotating lift seats, accessibility-focused engineering, and a fully open development model, the project reimagines mobility around real human movement rather than mechanical constraints. Built under the AGPL-3.0+ license, KineticKind invites a global community to collaborate on creating more inclusive transportation for everyone.

Circulis Aqua is an AGPL 3.0+ modular infrastructure design system for desalination, water purification, reuse, and geospatial distribution. It uses AI-assisted configuration to design scalable, plug-in water systems that range from residential units to municipal and regional grids. Built on a graph-based water flow model, it enables local-first optimization, closed-loop water reuse, and intelligent routing to ensure no water is wasted across interconnected infrastructure networks.

paper2code is an AI agent skill that converts arXiv papers into citation-anchored, runnable code. It includes ambiguity auditing, appendix mining, and human-in-the-loop enhancements contributed by Roxanne Ardary for interactive code refinement, experiment configuration, and verification of all implementation decisions.

Page-Agent is a JavaScript library that transforms any web page into an AI-driven interactive agent. It allows users and developers to control page elements and workflows using natural language commands, powered by large language models. With features like DOM manipulation, client-side execution, and optional human-in-the-loop confirmations, Page-Agent simplifies automation and enhances accessibility. The latest update includes end-to-end encryption (E2EE) for secure, private interactions.

OpenScreen is a free and open-source screen recording application for creating professional demos, tutorials, and presentations. It combines high-quality screen capture, smooth zoom effects, annotations, customizable backgrounds, and audio recording with emerging AI-assisted editing features and Human-in-the-Loop controls, giving users powerful automation while maintaining full creative oversight.

OpenProto is an open-source platform for discovering, evaluating, and optimizing hardware designs across public repositories, then converting them into fully sourced, manufacturable outputs for 3D printing, electronics, and other fabrication systems. It combines hardware intelligence, cost and performance optimization, and a human-in-the-loop approval system to ensure all designs are safe, buildable, and production-ready.

Aurelia Civic OS is a municipal-first civic operating system that coordinates real-world labor, services, and manufacturing through structured intent, verified skill networks, and locality-constrained execution. It prioritizes municipalities over broader regional systems, ensuring local economies remain primary in all routing, verification, and recommendation logic. The system combines an Intent Mesh routing engine, Skill Graph for individuals, and multi-layer trust verification to transform how communities discover, allocate, and execute real-world work.

Covenant AI is an open-source artificial intelligence infrastructure platform focused on human authority, bounded autonomy, transparency, privacy, and accountable AI execution. Built as a complete alternative to traditional AI agent frameworks, Covenant AI ensures that every AI action is authorized, explainable, revocable, and verifiable — creating intelligence systems that remain fully accountable to the people they serve.

LatticeOS is a modular, human-in-the-loop operating system for governed multi-agent AI orchestration, designed to provide structured execution, deterministic workflows, and full auditability. Built around event-sourced transparency and explicit governance controls, LatticeOS enables intelligent systems where every agent action becomes structured, traceable history while keeping humans in control of all critical decision-making.

Arq is a machine intelligence system for understanding, modeling, and evolving software architecture as a living, dynamic graph. It analyzes codebases as structured systems of modules, dependencies, and behaviors, then simulates how they change over time under real-world constraints. The goal is to make software architecture measurable, explainable, and continuously evolvable.

LexChangeFeed is an open-source legal intelligence infrastructure that monitors, structures, and analyzes evolving copyright law across jurisdictions. It continuously ingests statutes, case law, and regulatory updates, then connects them to a versioned legal knowledge graph to provide citation-backed explanations, jurisdiction-aware insights, and real-time notifications about potential legal changes affecting user-defined works.

Axis Juris is a modular, open-source legal intelligence system designed to analyze and structure patent law, case law, and jurisdiction-specific regulations. It combines a continuously updating legal knowledge graph with AI-driven reasoning to provide sourced, cross-referenced analysis of statutes and precedents. Built for scalability across U.S. federal and state systems (and extendable internationally), Axis Juris focuses on legal alignment, conflict detection, and structured understanding of evolving law.

PublicStack AI is an open-source system that analyzes software projects and recommends full open-source repositories to enhance or replace parts of a stack. Instead of suggesting code snippets, it focuses on system-level composition—helping developers build better software by assembling proven repositories from across the open-source ecosystem, with built-in license awareness and automatic attribution tracking.

VeritasCode is a retrieval-first, modular AI platform that analyzes laws across federal, state, and local jurisdictions to identify potential conflicts, inconsistencies, and constitutional questions. It uses evidence-based retrieval and full citation tracing to compare statutes, regulations, and case law without issuing legal judgments, focusing instead on transparent, explainable analysis for human review.

VoxPersona is a source-bound AI assistant platform that transforms approved content into interactive responses in text, voice, or AI-generated video. It delivers every answer with strict citations to original sources, ensuring transparency, traceability, and trust.

RAGBase is a schema-enforced infrastructure layer for building modular Retrieval-Augmented Generation (RAG) systems. It provides a strict, contract-driven architecture where every component—ingestion, embedding, retrieval, and generation—is defined by explicit input/output schemas and validated through a built-in spec hygiene layer. This ensures predictable behavior, prevents system drift, and enables safe module interchangeability in production-grade AI pipelines.